feat(diffusers): add experimental support for sd_embed-style prompt embedding #8504
+58
−0
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Description
Adds support for sd_embed-style prompt embedding for the models supported by it. This is the style portrayed in the diffusers weighted prompting doc, so I thought it would be good to support.
Feature is locked behind an environment variable (SD_EMBED=1) similar to compel-style prompt embedding (COMPEL=1).
Notes for Reviewers
I tested by building cuda13-diffusers locally and running some sd_embed-style prompts to verify it ran and honored the weights provided. I only currently have validated SDXL models.
Signed commits